Search results for: artificial intelligence based optimization

Authors: Samuel Nderitu Muchiri, Tracy Wangechi Maina

Abstract:

Truck drivers face a myriad of challenges in their profession. Enhancements in logistics effectiveness can be pivotal in propelling economic developments. The specific objective of the study was to assess the influence of driver distraction on crash risk. The study is significant as it elucidates best practices that truck drivers can embrace in an effort to enhance road safety. These include amalgamating behaviors that enable drivers to fruitfully execute multifaceted functions such as finding and following routes, evading collisions, monitoring speed, adhering to road regulations, and evaluating vehicle systems’ conditions. The analysis involved an empirical review of ten previous studies related to the research topic. The articles revealed that driver distraction plays a substantial role in road accidents and other crucial road security incidents across the globe. Africa depends immensely on the freight transport sector to facilitate supply chain operations. Several studies indicate that drivers who operate primarily on rural roads, such as those found in Sub-Saharan Africa, have an increased propensity to engage in distracted activities such as cell phone usage while driving. The findings also identified the need for digitalization in truck driving operations, including carrier management techniques such as fatigue management, artificial intelligence, and automating functions like cell phone usage controls. The recommendations can aid policymakers and commercial truck carriers in deepening their understanding of driver distraction and enforcing mitigations to foster road safety.

Keywords: truck drivers, distraction, digitalization, crash risk, road safety

Procedia PDF Downloads 53

Authors: Soha Saad, Jean Bigeon, Florence Ossart, Etienne Sourdille

Abstract:

Developing better solutions for train rescheduling problems has been drawing the attention of researchers for decades. Most researches in this field deal with minor incidents that affect a large number of trains due to cascading effects. They focus on timetables, rolling stock and crew duties, but do not take into account infrastructure limits. The present work addresses electric infrastructure incidents that limit the power available for train traction, and hence the transportation capacity of the railway system. Rescheduling is needed in order to optimally share the available power among the different trains. We propose a rescheduling process based on dynamic multiphysics railway simulations that include the mechanical and electrical properties of all the system components and calculate physical quantities such as the train speed profiles, voltage along the catenary lines, temperatures, etc. The optimization problem to solve has a large number of continuous and discrete variables, several output constraints due to physical limitations of the system, and a high computation cost. Our approach includes a phase of sensitivity analysis in order to analyze the behavior of the system and help the decision making process and/or more precise optimization. This approach is a quantitative method based on simulation statistics of the dynamic railway system, considering a predefined range of variation of the input parameters. Three important settings are defined. Factor prioritization detects the input variables that contribute the most to the outputs variation. Then, factor fixing allows calibrating the input variables which do not influence the outputs. Lastly, factor mapping is used to study which ranges of input values lead to model realizations that correspond to feasible solutions according to defined criteria or objectives. Generalized Sobol indexes are used for factor prioritization and factor fixing. The approach is tested in the case of a simple railway system, with a nominal traffic running on a single track line. The considered incident is the loss of a feeding power substation, which limits the power available and the train speed. Rescheduling is needed and the variables to be adjusted are the trains departure times, train speed reduction at a given position and the number of trains (cancellation of some trains if needed). The results show that the spacing between train departure times is the most critical variable, contributing to more than 50% of the variation of the model outputs. In addition, we identify the reduced range of variation of this variable which guarantees that the output constraints are respected. Optimal solutions are extracted, according to different potential objectives: minimizing the traveling time, the train delays, the traction energy, etc. Pareto front is also built.

Keywords: optimization, rescheduling, railway system, sensitivity analysis, train timetable

Procedia PDF Downloads 400

Authors: Marcio Leal, Marta Villamil

Abstract:

Computacional recognition of sign languages aims to allow a greater social and digital inclusion of deaf people through interpretation of their language by computer. This article presents a model of recognition of two of global parameters from sign languages; hand configurations and hand movements. Hand motion is captured through an infrared technology and its joints are built into a virtual three-dimensional space. A Multilayer Perceptron Neural Network (MLP) was used to classify hand configurations and Dynamic Time Warping (DWT) recognizes hand motion. Beyond of the method of sign recognition, we provide a dataset of hand configurations and motion capture built with help of fluent professionals in sign languages. Despite this technology can be used to translate any sign from any signs dictionary, Brazilian Sign Language (Libras) was used as case study. Finally, the model presented in this paper achieved a recognition rate of 80.4%.

Keywords: artificial neural network, computer vision, dynamic time warping, infrared, sign language recognition

Procedia PDF Downloads 219

Authors: M. K. Benhaoua, A. E. H. Benyamina, T. Djeradi, P. Boulet

Abstract:

In this paper, we propose adaptive routing that considers the routing of communications in order to optimize the overall performance. The routing technique uses a newly proposed Algorithm to route communications between the tasks. The routing we propose of the communications leads to a better optimization of several performance metrics (time and energy consumption). Experimental results show that the proposed routing approach provides significant performance improvements when compared to those using static routing.

Keywords: multi-processor systems-on-chip (mpsocs), network-on-chip (noc), heterogeneous architectures, adaptive routin

Procedia PDF Downloads 381

Authors: Mthiyane Pretty, Mitsui Toshiake, Nagano Hirohiko, Aycan Murat

Abstract:

Among the most significant greenhouse gases released from rice fields are methane and carbon dioxide. The primary focus of this research was to quantify CH₄ and CO₂ gas using different 4 rice cultivars, two water regimes, and a recording of soil moisture and temperature. In this study, we hypothesized that paddy field soils may directly affect soil enzymatic activities and physicochemical properties in the rhizosphere soil of paddy fields and subsequently indirectly affect the activity, abundance, diversity, and community composition of methanogens, ultimately affecting CH₄ flux. The experiment was laid out in the randomized block design with two treatments and three replications for each genotype. In two treatments, paddy fields and artificial soil were used. 35 days after planting (DAP), continuous flooding irrigation, Alternate wetting, and drying (AWD) were applied during the vegetative stage. The highest recorded measurements of soil and environmental parameters were soil moisture at 76%, soil temperature at 28.3℃, Bulk EC at 0.99 ds/m, and pore water EC at 1,25, using HydraGO portable soil sensor system. Gas samples were carried out once on a weekly basis at 09:00 am and 12: 00 pm to obtain the mean GHG flux. Gas Chromatography (GC, Shimadzu, GC-2010, Japan) was used for the analysis of CH4 and CO₂. The treatments with paddy field soil had a 1.3℃ higher temperature than artificial soil. The overall changes in Bulk EC were not significant across the treatment. The CH₄ emission patterns were observed in all rice genotypes, although they were less in treatments with AWD with artificial soil. This shows that AWD creates oxic conditions in the rice soil. CO₂ was also quantified, but it was in minute quantities, as rice plants were using CO₂ for photosynthesis. The highest tillering number was 7, and the lowest was 3 in cultivars grown. The rice varieties to be used for breeding are Norin 24, with showed a high number of tillers with less CH₄.

Keywords: greenhouse gases, methane, morphological characterization, alternating wetting and drying

Procedia PDF Downloads 83

Authors: Wentian Shi, Daming Shi, Maysam Orouskhani, Feng Tian

Abstract:

Whereas currently the most prevalent deep learning methods require a large amount of data for training, few-shot learning tries to learn a model from limited data without extensive retraining. In this paper, we present a loss function based on triplet loss for solving few-shot problem using metric based learning. Instead of setting the margin distance in triplet loss as a constant number empirically, we propose an adaptive margin distance strategy to obtain the appropriate margin distance automatically. We implement the strategy in the deep siamese network for deep metric embedding, by utilizing an optimization approach by penalizing the worst case and rewarding the best. Our experiments on image recognition and co-segmentation model demonstrate that using our proposed triplet loss with adaptive margin distance can significantly improve the performance.

Keywords: few-shot learning, triplet network, adaptive margin, deep learning

Procedia PDF Downloads 174

Authors: Ahmed Noor Al-qayyim, Barlas Özden Çağlayan

Abstract:

Structural failure is caused mainly by damage that often occurs on structures. Many researchers focus on obtaining very efficient tools to detect the damage in structures in the early state. In the past decades, a subject that has received considerable attention in literature is the damage detection as determined by variations in the dynamic characteristics or response of structures. This study presents a new damage identification technique. The technique detects the damage location for the incomplete structure system using output data only. The method indicates the damage based on the free vibration test data by using “Two Points - Condensation (TPC) technique”. This method creates a set of matrices by reducing the structural system to two degrees of freedom systems. The current stiffness matrices are obtained from optimization of the equation of motion using the measured test data. The current stiffness matrices are compared with original (undamaged) stiffness matrices. High percentage changes in matrices’ coefficients lead to the location of the damage. TPC technique is applied to the experimental data of a simply supported steel beam model structure after inducing thickness change in one element. Where two cases are considered, the method detects the damage and determines its location accurately in both cases. In addition, the results illustrate that these changes in stiffness matrix can be a useful tool for continuous monitoring of structural safety using ambient vibration data. Furthermore, its efficiency proves that this technique can also be used for big structures.

Keywords: damage detection, optimization, signals processing, structural health monitoring, two points–condensation

Procedia PDF Downloads 367

Authors: Vipul M. Patel, Hemantkumar B. Mehta

Abstract:

Technological innovations in electronic world demand novel, compact, simple in design, less costly and effective heat transfer devices. Closed Loop Pulsating Heat Pipe (CLPHP) is a passive phase change heat transfer device and has potential to transfer heat quickly and efficiently from source to sink. Thermal performance of a CLPHP is governed by various parameters such as number of U-turns, orientations, input heat, working fluids and filling ratio. The present paper is an attempt to predict the thermal performance of a CLPHP using Artificial Neural Network (ANN). Filling ratio and heat input are considered as input parameters while thermal resistance is set as target parameter. Types of neural networks considered in the present paper are radial basis, generalized regression, linear layer, cascade forward back propagation, feed forward back propagation; feed forward distributed time delay, layer recurrent and Elman back propagation. Linear, logistic sigmoid, tangent sigmoid and Radial Basis Gaussian Function are used as transfer functions. Prediction accuracy is measured based on the experimental data reported by the researchers in open literature as a function of Mean Absolute Relative Deviation (MARD). The prediction of a generalized regression ANN model with spread constant of 4.8 is found in agreement with the experimental data for MARD in the range of ±1.81%.

Keywords: ANN models, CLPHP, filling ratio, generalized regression, spread constant

Procedia PDF Downloads 296

Authors: Foozhan Gharehkhani

Abstract:

The use of solar energy as a sustainable renewable energy source has gained significant attention in recent years. Solar concentrating systems (CSP), which direct solar radiation onto a receiver, are an effective means of producing high-temperature thermal energy. Cavity receivers, known for their high thermal efficiency and reduced heat losses, are particularly noteworthy in these systems. Optimizing their design can enhance energy efficiency and reduce costs. This study leverages the genetic algorithm, a powerful optimization tool inspired by natural evolution, to optimize the performance of a solar concentrator system with a cavity receiver, aiming for a more efficient and cost-effective design. In this study, a system consisting of a solar concentrator and a cavity receiver was analyzed. The concentrator was designed as a parabolic dish, and the receiver had a cylindrical cavity with a helical structure. The primary parameters were defined as the cavity diameter (D), the receiver height (h), and the helical pipe diameter (d). Initially, the system was optimized to achieve the maximum heat flux, and the optimal parameter values along with the maximum heat flux were obtained. Subsequently, a multi-objective optimization approach was applied, aiming to maximize the heat flux while minimizing the system construction cost. The optimization process was conducted using the genetic algorithm implemented in MATLAB with precise execution. The results of this study revealed that the optimal dimensions of the receiver, including the cavity diameter (D), receiver height (h), and helical pipe diameter (d), were determined to be 0.142 m, 0.1385 m, and 0.011 m, respectively. This optimization resulted in improvements of 3% in the cavity diameter, 8% in the height, and 5% in the helical pipe diameter. Furthermore, the results indicated that the primary focus of this research was the accurate thermal modeling of the solar collection system. The simulations and the obtained results demonstrated that the optimization applied to this system maximized its thermal performance and elevated its energy efficiency to a desirable level. Moreover, this study successfully modeled and controlled effective temperature variations at different angles of solar irradiation, highlighting significant improvements in system efficiency. The significance of this research lies in leveraging solar energy as one of the prominent renewable energy sources, playing a key role in replacing fossil fuels. Considering the environmental and economic challenges associated with the excessive use of fossil resources—such as increased greenhouse gas emissions, environmental degradation, and the depletion of fossil energy reserves—developing technologies related to renewable energy has become a vital priority. Among these, solar concentrating systems, capable of achieving high temperatures, are particularly important for industrial and heating applications. This research aims to optimize the performance of such systems through precise design and simulation, making a significant contribution to the advancement of advanced technologies and the efficient utilization of solar energy in Iran, thereby addressing the country's future energy needs effectively.

Keywords: cavity receiver, genetic algorithm, optimization, solar concentrator system performance

Procedia PDF Downloads 15

Authors: Yu-Lin Shen, Ming-Kuen Chang

Abstract:

In addition to a considerable amount of machinery and equipment, intricacies of the transmission pipeline exist in Petrochemical plants. Long term corrosion may lead to pipeline thinning and rupture, causing serious safety concerns. With the advances in non-destructive testing technology, more rapid and long-range ultrasonic detection techniques are often used for pipeline inspection, EMAT without coupling to detect, it is a non-contact ultrasonic, suitable for detecting elevated temperature or roughened e surface of line. In this study, we prepared artificial defects in pipeline for Electromagnetic Acoustic Transducer testing (EMAT) to survey the relationship between the defect location, sizing and the EMAT signal. It was found that the signal amplitude of EMAT exhibited greater signal attenuation with larger defect depth and length. In addition, with bigger flat hole diameter, greater amplitude attenuation was obtained. In summary, signal amplitude attenuation of EMAT was affected by the defect depth, defect length and the hole diameter and size.

Keywords: EMAT, artificial defect, NDT, ultrasonic testing

Procedia PDF Downloads 354

Authors: Riyadh Jamegh, Alla Eldin Kassam, Sawsan Sabih

Abstract:

In order to overcome uncertainty conditions and inability to meet customers' requests due to these conditions, organizations tend to reserve a certain safety stock level (SSL). This level must be chosen carefully in order to avoid the increase in holding cost due to excess in SSL or shortage cost due to too low SSL. This paper used soft computing fuzzy logic to identify optimal SSL; this fuzzy model uses the dynamic concept to cope with high complexity environment status. The proposed model can deal with three input variables, i.e., demand stability level, raw material availability level, and on hand inventory level by using dynamic fuzzy logic to obtain the best SSL as an output. In this model, demand stability, raw material, and on hand inventory levels are described linguistically and then treated by inference rules of the fuzzy model to extract the best level of safety stock. The aim of this research is to provide dynamic approach which is used to identify safety stock level, and it can be implanted in different industries. Numerical case study in the dairy industry with Yogurt 200 gm cup product is explained to approve the validity of the proposed model. The obtained results are compared with the current level of safety stock which is calculated by using the traditional approach. The importance of the proposed model has been demonstrated by the significant reduction in safety stock level.

Keywords: inventory optimization, soft computing, safety stock optimization, dairy industries inventory optimization

Procedia PDF Downloads 129

Authors: Tunahan Sapmaz, Harun Etçi, İbrahim Şenol, Yasemin Öner

Abstract:

Rotor bar dimensions have a great influence on the air-gap magnetic flux density. Therefore, poor selection of this parameter during the machine design phase causes the air-gap magnetic flux density to be distorted. Thus, it causes noise, torque fluctuation, and losses in the induction motor. On the other hand, the change in rotor bar dimensions will change the resistance of the conductor, so the current will be affected. Therefore, the increase and decrease of rotor bar current affect operation, starting torque, and efficiency. The aim of this study is to examine the effect of rotor bar dimensions on the electromagnetic performance criteria of the induction motor. Modeling of the induction motor is done by the finite element method (FEM), which is a very powerful tool. In FEM, the results generally focus on performance criteria such as torque, torque fluctuation, efficiency, and current.

Keywords: induction motor, finite element method, optimization, rotor bar

Procedia PDF Downloads 131

Authors: R. Rama Kishore, Sunesh

Abstract:

Nowadays, robust and secure watermarking algorithm and its optimization have been need of the hour. A watermarking algorithm is presented to achieve the copy right protection of the owner based on visual cryptography, histogram shape property and entropy. In this, both host image and watermark are preprocessed. Host image is preprocessed by using Butterworth filter, and watermark is with visual cryptography. Applying visual cryptography on water mark generates two shares. One share is used for embedding the watermark, and the other one is used for solving any dispute with the aid of trusted authority. Usage of histogram shape makes the process more robust against geometric and signal processing attacks. The combination of visual cryptography, Butterworth filter, histogram, and entropy can make the algorithm more robust, imperceptible, and copy right protection of the owner.

Keywords: digital watermarking, visual cryptography, histogram, butter worth filter

Procedia PDF Downloads 362

Authors: Wenjuan Lu

Abstract:

China and Hungary have risen from a friendly and comprehensive cooperative relationship to a comprehensive strategic partnership in recent years, and the economic and trade relations between the two countries have developed smoothly. As an important country along the ‘Belt and Road’, Hungary and China have strong economic complementarities and have unique advantages in carrying China's industrial transfer and economic transformation and development. The construction of the China-Hungary Economic and Trade Cooperation Zone, which was initiated by the ‘Sino-Hungarian Borsod Industrial Zone’ and the ‘Hungarian Central European Trade and Logistics Cooperation Park’ has promoted infrastructure construction, optimized production capacity, promoted industrial restructuring, and formed brand and agglomeration effects. Enhancing the influence of Chinese companies in the European market has also promoted economic development in Hungary and even in Central and Eastern Europe. However, as the China-Hungary Economic and Trade Cooperation Zone is still in its infancy, there are still shortcomings such as small scale, single function, and no prominent platform. In the future, based on the needs of China's cooperation with ‘17+1’ and China-Hungary cooperation, on the basis of appropriately expanding the scale of economic and trade cooperation zones and appropriately increasing the number of economic and trade cooperation zones, it is better to focus on optimizing and adjusting its functions and highlighting different economic and trade cooperation. The differentiated function of the trade zones strengthens the multi-faceted cooperation of economic and trade cooperation zones and highlights its role as a platform for cooperation in information, capital, and services.

Keywords: ‘One Belt, One Road’ Initiative, China-Hungary economic and trade cooperation zone, function optimization, Central and Eastern Europe

Procedia PDF Downloads 184

Authors: Jarek Krajewski, Andre Wittenborn, Martin Sauerland

Abstract:

This abstract describes a promising approach for estimating post-traumatic stress disorder (PTSD) based on prosodic speech characteristics. It illustrates the validity of this method by briefly discussing results from an Arabic refugee sample (N= 47, 32 m, 15 f). A well-established standardized self-report scale “Reaction of Adolescents to Traumatic Stress” (RATS) was used to determine the ground truth level of PTSD. The speech material was prompted by telling about autobiographical related sadness inducing experiences (sampling rate 16 kHz, 8 bit resolution). In order to investigate PTSD-induced speech changes, a self-developed set of 136 prosodic speech features was extracted from the .wav files. This set was adapted to capture traumatization related speech phenomena. An artificial neural network (ANN) machine learning model was applied to determine the PTSD level and reached a correlation of r = .37. These results indicate that our classifiers can achieve similar results to those seen in speech-based stress research.

Keywords: speech prosody, PTSD, machine learning, feature extraction

Procedia PDF Downloads 94

Authors: Gaylord K. Booto, Marinelli Giuseppe, Helge Brattebø, Rolf A. Bohne

Abstract:

Emissions reduction has emerged among the principal targets in the process of planning and designing road alignments today. Intelligent road design methods that can result in optimized alignment constitute concrete and innovative responses towards better alternatives and more sustainable road infrastructures. As the largest amount of emissions of road infrastructures occur in the operation stage, it becomes very important to consider traffic weight and distribution in alignment design process. This study analyzes the effects of four traffic factors (i.e. operating speed, vehicle category, technology and fuel type) on adjusting the vertical alignment of a given road, using optimization techniques. Further, factors’ effects are assessed qualitatively and quantitatively, and the emission profiles of resulting alignment alternatives are compared.

Keywords: alignment adjustment, emissions reduction, optimization, traffic-oriented

Procedia PDF Downloads 373

Authors: Pedro J. Rolim-Neto, Leslie R. M. Ferraz, Fabiana L. A. Santos, Pablo A. Ferreira, Ricardo T. L. Maia-Jr., Magaly A. M. Lyra, Danilo A F. Fonte, Salvana P. M. Costa, Amanda C. Q. M. Vieira, Larissa A. Rolim

Abstract:

Initially developed as an antimalarial agent, hydroxychloroquine (HCQ) sulfate is often used as a slow-acting antirheumatic drug in the treatment of disorders of connective tissue. The United States Pharmacopeia (USP) 37 provides a reversed-phase HPLC method for quantification of HCQ. However, this method was not reproducible, producing asymmetric peaks in a long analysis time. The asymmetry of the peak may cause an incorrect calculation of the concentration of the sample. Furthermore, the analysis time is unacceptable, especially regarding the routine of a pharmaceutical industry. The aiming of this study was to develop a fast, easy and efficient method for quantification of HCQ sulfate by High Performance Liquid Chromatography (HPLC) based on the Quality by Design (QbD) methodology. This method was optimized in terms of peak symmetry using the surface area graphic as the Design of Experiments (DoE) and the tailing factor (TF) as an indicator to the Design Space (DS). The reference method used was that described at USP 37 to the quantification of the drug. For the optimized method, was proposed a 33 factorial design, based on the QbD concepts. The DS was created with the TF (in a range between 0.98 and 1.2) in order to demonstrate the ideal analytical conditions. Changes were made in the composition of the USP mobile-phase (USP-MP): USP-MP: Methanol (90:10 v/v, 80:20 v/v and 70:30 v/v), in the flow (0.8, 1.0 and 1.2 mL) and in the oven temperature (30, 35, and 40ºC). The USP method allowed the quantification of drug in a long time (40-50 minutes). In addition, the method uses a high flow rate (1,5 mL.min-1) which increases the consumption of expensive solvents HPLC grade. The main problem observed was the TF value (1,8) that would be accepted if the drug was not a racemic mixture, since the co-elution of the isomers can become an unreliable peak integration. Therefore, the optimization was suggested in order to reduce the analysis time, aiming a better peak resolution and TF. For the optimization method, by the analysis of the surface-response plot it was possible to confirm the ideal setting analytical condition: 45 °C, 0,8 mL.min-1 and 80:20 USP-MP: Methanol. The optimized HPLC method enabled the quantification of HCQ sulfate, with a peak of high resolution, showing a TF value of 1,17. This promotes good co-elution of isomers of the HCQ, ensuring an accurate quantification of the raw material as racemic mixture. This method also proved to be 18 times faster, approximately, compared to the reference method, using a lower flow rate, reducing even more the consumption of the solvents and, consequently, the analysis cost. Thus, an analytical method for the quantification of HCQ sulfate was optimized using QbD methodology. This method proved to be faster and more efficient than the USP method, regarding the retention time and, especially, the peak resolution. The higher resolution in the chromatogram peaks supports the implementation of the method for quantification of the drug as racemic mixture, not requiring the separation of isomers.

Keywords: analytical method, hydroxychloroquine sulfate, quality by design, surface area graphic

Procedia PDF Downloads 643

Authors: Nikhil Kumar, Asish Bandyopadhyay

Abstract:

Laser welding process is a capable technology for forming the automobile, microelectronics, marine and aerospace parts etc. In the present work, a mathematical and statistical approach is adopted to study the laser welding of AISI 304 stainless steel. A robotic control 500 W pulsed Nd:YAG laser source with 1064 nm wavelength has been used for welding purpose. Butt joints are made. The effects of welding parameters, namely; laser power, scanning speed and pulse width on the seam width and depth of penetration has been investigated using the empirical models developed by response surface methodology (RSM). Weld quality is directly correlated with the weld geometry. Twenty sets of experiments have been conducted as per central composite design (CCD) design matrix. The second order mathematical model has been developed for predicting the desired responses. The results of ANOVA indicate that the laser power has the most significant effect on responses. Microstructural analysis as well as hardness of the selected weld specimens has been carried out to understand the metallurgical and mechanical behaviour of the weld. Average micro-hardness of the weld is observed to be higher than the base metal. Higher hardness of the weld is the resultant of grain refinement and δ-ferrite formation in the weld structure. The result suggests that the lower line energy generally produce fine grain structure and improved mechanical properties than the high line energy. The combined effects of input parameters on responses have been analyzed with the help of developed 3-D response surface and contour plots. Finally, multi-objective optimization has been conducted for producing weld joint with complete penetration, minimum seam width and acceptable welding profile. Confirmatory tests have been conducted at optimum parametric conditions to validate the applied optimization technique.

Keywords: ANOVA, laser welding, modeling and optimization, response surface methodology

Procedia PDF Downloads 297

Authors: J.P. Henriques, E. R. Neto, G. Almeida, G. Ribeiro, J.V. Coutinho, A.B. Lugli

Abstract:

Industry 4.0, or the Fourth Industrial Revolution, is transforming the relationship between people and machines. In this scenario, some technologies such as Cloud Computing, Internet of Things, Augmented Reality, Artificial Intelligence, Additive Manufacturing, among others, are making industries and devices increasingly intelligent. One of the most powerful technologies of this new revolution is the Digital Twin, which allows the virtualization of a real system or process. In this context, the present paper addresses the linear and nonlinear dynamic study of a didactic level plant using Digital Twin. In the first part of the work, the level plant is identified at a fixed point of operation, BY using the existing method of least squares means. The linearized model is embedded in a Digital Twin using Automation Studio® from Famous Technologies. Finally, in order to validate the usage of the Digital Twin in the linearized study of the plant, the dynamic response of the real system is compared to the Digital Twin. Furthermore, in order to develop the nonlinear model on a Digital Twin, the didactic level plant is identified by using the method proposed by Hammerstein. Different steps are applied to the plant, and from the Hammerstein algorithm, the nonlinear model is obtained for all operating ranges of the plant. As for the linear approach, the nonlinear model is embedded in the Digital Twin, and the dynamic response is compared to the real system in different points of operation. Finally, yet importantly, from the practical results obtained, one can conclude that the usage of Digital Twin to study the dynamic systems is extremely useful in the industrial environment, taking into account that it is possible to develop and tune controllers BY using the virtual model of the real systems.

Keywords: industry 4.0, digital twin, system identification, linear and nonlinear models

Procedia PDF Downloads 153

Authors: B. Sajeena Beevi, P. P. Jose, G. Madhu

Abstract:

The aim of this study was to obtain the optimal conditions for biogas production from anaerobic digestion of organic fraction of municipal solid waste (OFMSW) using response surface methodology (RSM). The parameters studied were initial pH, substrate concentration and total organic carbon (TOC). The experimental results showed that the linear model terms of initial pH and substrate concentration and the quadratic model terms of the substrate concentration and TOC had significant individual effect (p < 0.05) on biogas yield. However, there was no interactive effect between these variables (p > 0.05). The highest level of biogas produced was 53.4 L/Kg VS at optimum pH, substrate concentration and total organic carbon of 6.5, 99gTS/L, and 20.32 g/L respectively.

Keywords: anaerobic digestion, biogas, optimization, response surface methodology

Procedia PDF Downloads 440

Authors: Saahith M. S., Sivakami R.

Abstract:

In the realm of football analytics, particularly focusing on predicting football player performance, the ability to forecast player success accurately is of paramount importance for teams, managers, and fans. This study introduces an elaborate examination of predicting football player performance through the integration of data visualization methods and machine learning algorithms. The research entails the compilation of an extensive dataset comprising player attributes, conducting data preprocessing, feature selection, model selection, and model training to construct predictive models. The analysis within this study will involve delving into feature significance using methodologies like Select Best and Recursive Feature Elimination (RFE) to pinpoint pertinent attributes for predicting player performance. Various machine learning algorithms, including Random Forest, Decision Tree, Linear Regression, Support Vector Regression (SVR), and Artificial Neural Networks (ANN), will be explored to develop predictive models. The evaluation of each model's performance utilizing metrics such as Mean Squared Error (MSE) and R-squared will be executed to gauge their efficacy in predicting player performance. Furthermore, this investigation will encompass a top player analysis to recognize the top-performing players based on the anticipated overall performance scores. Nationality analysis will entail scrutinizing the player distribution based on nationality and investigating potential correlations between nationality and player performance. Positional analysis will concentrate on examining the player distribution across various positions and assessing the average performance of players in each position. Age analysis will evaluate the influence of age on player performance and identify any discernible trends or patterns associated with player age groups. The primary objective is to predict a football player's overall performance accurately based on their individual attributes, leveraging data-driven insights to enrich the comprehension of player success on the field. By amalgamating data visualization and machine learning methodologies, the aim is to furnish valuable tools for teams, managers, and fans to effectively analyze and forecast player performance. This research contributes to the progression of sports analytics by showcasing the potential of machine learning in predicting football player performance and offering actionable insights for diverse stakeholders in the football industry.

Keywords: football analytics, player performance prediction, data visualization, machine learning algorithms, random forest, decision tree, linear regression, support vector regression, artificial neural networks, model evaluation, top player analysis, nationality analysis, positional analysis

Procedia PDF Downloads 41

Authors: Martins Y. Otache, John J. Musa, Abayomi I. Kuti, Mustapha Mohammed

Abstract:

The performance of an artificial neural network (ANN) is contingent on a host of factors, for instance, the network optimisation scheme. In view of this, the study examined the general implications of the ANN training optimisation algorithm on its forecast performance. To this end, the Bayesian regularisation (Br), Levenberg-Marquardt (LM), and the adaptive learning gradient descent: GDM (with momentum) algorithms were employed under different ANN structural configurations: (1) single-hidden layer, and (2) double-hidden layer feedforward back propagation network. Results obtained revealed generally that the gradient descent with momentum (GDM) optimisation algorithm, with its adaptive learning capability, used a relatively shorter time in both training and validation phases as compared to the Levenberg- Marquardt (LM) and Bayesian Regularisation (Br) algorithms though learning may not be consummated; i.e., in all instances considering also the prediction of extreme flow conditions for 1-day and 5-day ahead, respectively especially using the ANN model. In specific statistical terms on the average, model performance efficiency using the coefficient of efficiency (CE) statistic were Br: 98%, 94%; LM: 98 %, 95 %, and GDM: 96 %, 96% respectively for training and validation phases. However, on the basis of relative error distribution statistics (MAE, MAPE, and MSRE), GDM performed better than the others overall. Based on the findings, it is imperative to state that the adoption of ANN for real-time forecasting should employ training algorithms that do not have computational overhead like the case of LM that requires the computation of the Hessian matrix, protracted time, and sensitivity to initial conditions; to this end, Br and other forms of the gradient descent with momentum should be adopted considering overall time expenditure and quality of the forecast as well as mitigation of network overfitting. On the whole, it is recommended that evaluation should consider implications of (i) data quality and quantity and (ii) transfer functions on the overall network forecast performance.

Keywords: streamflow, neural network, optimisation, algorithm

Procedia PDF Downloads 158

Authors: Flora Elvistia Firdaus

Abstract:

The chemical structure of soybean oils have to be chemically modified through its tryglyceride to attain resemblance properties with petrochemicals. Sulfur acid catalyst in peracetic acid co-reagent has good performance on modified soybean oil strucutures through its unsaturated fatty acid moiety to the desired hydroxyl functional groups. A series of screening reactions have indicated that the ratio of acetic/peroxide acid 1:7.25 (mol/mol) with temperature of 600°C for soy-epoxide synthesis are prevailed for up-scaling of bodied soybean into 10 and 20 folds from initials. A two-step process was conducted for the preparation of soy-polyol in designated temperatures.

Keywords: soybean, polyol, up-scaling, polyurethane

Procedia PDF Downloads 366

Authors: Alireza Dantism

Abstract:

Presently, describing the function of a protein sequence is one of the most common problems in biology. Usually, this problem can be facilitated by studying the three-dimensional structure of proteins. In the absence of a protein structure, comparative modeling often provides a useful three-dimensional model of the protein that is dependent on at least one known protein structure. Comparative modeling predicts the three-dimensional structure of a given protein sequence (target) mainly based on its alignment with one or more proteins of known structure (templates). Comparative modeling consists of four main steps 1. Similarity between the target sequence and at least one known template structure 2. Alignment of target sequence and template(s) 3. Build a model based on alignment with the selected template(s). 4. Prediction of model errors 5. Optimization of the built model There are many computer programs and web servers that automate the comparative modeling process. One of the most important advantages of these servers is that it makes comparative modeling available to both experts and non-experts, and they can easily do their own modeling without the need for programming knowledge, but some other experts prefer using programming knowledge and do their modeling manually because by doing this they can maximize the accuracy of their modeling. In this study, a web-based tool has been designed to predict the tertiary structure of proteins using PHP and Python programming languages. This tool is called EasyModel. EasyModel can receive, according to the user's inputs, the desired unknown sequence (which we know as the target) in this study, the protein sequence file (template), etc., which also has a percentage of similarity with the primary sequence, and its third structure Predict the unknown sequence and present the results in the form of graphs and constructed protein files.

Keywords: structural bioinformatics, protein tertiary structure prediction, modeling, comparative modeling, modeller

Procedia PDF Downloads 102

Authors: Xiyang Li, Qi Yu, Lun Zhang

Abstract:

In the face of natural disasters and other emergency situations, determining the optimal location of rescue centers is crucial for improving rescue efficiency and minimizing impact on affected populations. This paper proposes a method that integrates genetic algorithms (GA) and backpropagation neural networks (BPNN) to address the site selection optimization problem for emergency rescue centers. We utilize BPNN to accurately estimate the cost of delivering supplies from rescue centers to each temporary camp. Moreover, a genetic algorithm with a special partially matched crossover (PMX) strategy is employed to ensure that the number of temporary camps assigned to each rescue center adheres to predetermined limits. Using the population distribution data during the 2022 epidemic in Jiading District, Shanghai, as an experimental case, this paper verifies the effectiveness of the proposed method. The experimental results demonstrate that the BPNN-GA method proposed in this study outperforms existing algorithms in terms of computational efficiency and optimization performance. Especially considering the requirements for computational resources and response time in emergency situations, the proposed method shows its ability to achieve rapid convergence and optimal performance in the early and mid-stages. Future research could explore incorporating more real-world conditions and variables into the model to further improve its accuracy and applicability.

Keywords: emergency rescue centers, genetic algorithms, back-propagation neural networks, site selection optimization

Procedia PDF Downloads 93

Authors: Hayriye Anıl, Görkem Kar

Abstract:

In addition to being rich in renewable energy resources, Turkey is one of the countries that promise potential in geothermal energy production with its high installed power, cheapness, and sustainability. Increasing imbalance penalties become an economic burden for organizations since geothermal generation plants cannot maintain the balance of supply and demand due to the inadequacy of the production forecasts given in the day-ahead market. A better production forecast reduces the imbalance penalties of market participants and provides a better imbalance in the day ahead market. In this study, using machine learning, deep learning, and, time series methods, the total generation of the power plants belonging to Zorlu Natural Electricity Generation, which has a high installed capacity in terms of geothermal, was estimated for the first one and two weeks of March, then the imbalance penalties were calculated with these estimates and compared with the real values. These modeling operations were carried out on two datasets, the basic dataset and the dataset created by extracting new features from this dataset with the feature engineering method. According to the results, Support Vector Regression from traditional machine learning models outperformed other models and exhibited the best performance. In addition, the estimation results in the feature engineering dataset showed lower error rates than the basic dataset. It has been concluded that the estimated imbalance penalty calculated for the selected organization is lower than the actual imbalance penalty, optimum and profitable accounts.

Keywords: machine learning, deep learning, time series models, feature engineering, geothermal energy production forecasting

Procedia PDF Downloads 114

Authors: Parth Mehta, Vedasri Bai Khavala, Prabhu Rajagopal, Tiju Thomas

Abstract:

There is an increasing need for alternative clean fuels, and hydrogen (H₂) has long been considered a promising solution with a high calorific value (142MJ/kg). However, the storage of H₂ and expensive processes for its generation have hindered its usage. Sodium borohydride (NaBH₄) can potentially be used as an economically viable means of H₂ storage. Thus far, there have been attempts to optimize the life of NaBH₄ (half-life) in aqueous media by stabilizing it with sodium hydroxide (NaOH) for various pH values. Other reports have shown that H₂ yield and reaction kinetics remained constant for all ratios of H₂O to NaBH₄ > 30:1, without any acidic catalysts. Here we highlight the importance of pH and H₂O: NaBH₄ ratio (80:1, 40:1, 20:1 and 10:1 by weight), for NaBH₄ stabilization (half-life reaction time at room temperature) and corrosion minimization of H₂ reactor components. It is interesting to observe that at any particular pH>10 (e.g., pH = 10, 11 and 12), the H₂O: NaBH₄ ratio does not have the expected linear dependence with stability. On the contrary, high stability was observed at the ratio of 10:1 H₂O: NaBH₄ across all pH>10. When the H₂O: NaBH₄ ratio is increased from 10:1 to 20:1 and beyond (till 80:1), constant stability (% degradation) is observed with respect to time. For practical usage (consumption within 6 hours of making NaBH₄ solution), 15% degradation at pH 11 and NaBH₄: H₂O ratio of 10:1 is recommended. Increasing this ratio demands higher NaOH concentration at the same pH, thus requiring a higher concentration or volume of acid (e.g., HCl) for H₂ generation. The reactions are done with tap water to render the results useful from an industrial standpoint. The observed stability regimes are rationalized based on complexes associated with NaBH₄ when solvated in water, which depend sensitively on both pH and NaBH₄: H₂O ratio.

Keywords: hydrogen, sodium borohydride, stability optimization, H₂O:NaBH₄ ratio

Procedia PDF Downloads 127

Authors: Hanbey Hazar, Hakan Gul

Abstract:

In this study, Thermal Barrier Coating (TBC) application is performed in order to reduce the engine emissions. Piston, exhaust, and intake valves of a single-cylinder four-cycle gasoline engine were coated with chromium carbide (Cr3C2) at a thickness of 300 µm by using the Plasma Spray coating method which is a TBC method. Gasoline engine was converted into an LPG system. The study was conducted in 4 stages. In the first stage, the piston, exhaust, and intake valves of the gasoline engine were coated with Cr3C2. In the second stage, gasoline engine was converted into the LPG system and the emission values in this engine were recorded. In the third stage, the experiments were repeated under the same conditions with a standard (uncoated) engine and the results were recorded. In the fourth stage, data obtained from both engines were loaded on Artificial Neural Networks (ANN) and estimated values were produced for every revolution. Thus, mathematical modeling of coated and uncoated engines was performed by using ANN. While there was a slight increase in exhaust gas temperature (EGT) of LPG engine due to TBC, carbon monoxide (CO) values decreased.

Keywords: LPG fuel, thermal barrier coating, artificial neural network, mathematical modelling

Procedia PDF Downloads 431

Authors: Lu Song Ma Li Zhi

Abstract:

With the rapid advancement of artificial intelligence technology, large language models (LLMs) have become a milestone in the field of natural language processing, demonstrating remarkable capabilities in semantic understanding, intelligent question answering, and text generation. These models are gradually penetrating various industries, particularly showcasing significant application potential in the data analysis domain. However, retraining or fine-tuning these models requires substantial computational resources and ample downstream task datasets, which poses a significant challenge for many enterprises and research institutions. Without modifying the internal parameters of the large models, prompt engineering techniques can rapidly adapt these models to new domains. This paper proposes a prompt design strategy aimed at leveraging the capabilities of large language models to automate the generation of data analysis code. By carefully designing prompts, data analysis requirements can be described in natural language, which the large language model can then understand and convert into executable data analysis code, thereby greatly enhancing the efficiency and convenience of data analysis. This strategy not only lowers the threshold for using large models but also significantly improves the accuracy and efficiency of data analysis. Our approach includes requirements for the precision of natural language descriptions, coverage of diverse data analysis needs, and mechanisms for immediate feedback and adjustment. Experimental results show that with this prompt design strategy, large language models perform exceptionally well in multiple data analysis tasks, generating high-quality code and significantly shortening the data analysis cycle. This method provides an efficient and convenient tool for the data analysis field and demonstrates the enormous potential of large language models in practical applications.

Keywords: large language models, prompt design, data analysis, code generation

Procedia PDF Downloads 48

Authors: Goutam Dubey, Varun Dutta

Abstract:

In the present study, rotary-electro discharge machining of EN31 tool steel has been carried out using a pure copper electrode. Various response variables such as Material Removal Rate (MRR), Tool Wear Rate (TWR), and Machining Rate (MR) have been studied against the selected process variables. The selected process variables were peak current (I), voltage (V), duty cycle, and electrode rotation (N). EN31 Tool Steel is hardened, high carbon steel which increases its hardness and reduces its machinability. Reduced machinability means it not economical to use conventional methods to machine EN31 Tool Steel. So, non-conventional methods play an important role in machining of such materials.

Keywords: electric discharge machining, EDM, tool steel, tool wear rate, optimization techniques

Procedia PDF Downloads 205